Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1724 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2867. Min Range: -7.2867
Max Act: 7.2867. Min Act: -0.1700
Data Index: 1857789 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2867. Min Range: -7.2867
Max Act: 7.0679. Min Act: -0.1700
Data Index: 6149584 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2867. Min Range: -7.2867
Max Act: 7.0367. Min Act: -0.1700
Data Index: 4653452 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2867. Min Range: -7.2867
Max Act: 7.0054. Min Act: -0.1700
Data Index: 1398770 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.9742. Min Act: -0.1700
Data Index: 7126239 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.9742. Min Act: -0.1700
Data Index: 8507066 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.9742. Min Act: -0.1700
Data Index: 5055045 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.9429. Min Act: -0.1700
Data Index: 6590684 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.9429. Min Act: -0.1700
Data Index: 7672769 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8492. Min Act: -0.1700
Data Index: 3059956 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8804. Min Act: -0.1700
Data Index: 1932003 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8492. Min Act: -0.1700
Data Index: 4409683 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8492. Min Act: -0.1700
Data Index: 5840952 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8179. Min Act: -0.1700
Data Index: 6414389 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8179. Min Act: -0.1700
Data Index: 2365177 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8179. Min Act: -0.1700
Data Index: 6855134 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8179. Min Act: -0.1700
Data Index: 4194051 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8179. Min Act: -0.1700
Data Index: 6790859 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.7867. Min Act: -0.1700
Data Index: 2901043 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2867. Min Range: -7.2867
Max Act: 6.8179. Min Act: -0.1700
Data Index: 5471651 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19